Rakesh

使用正则表达式。

前任:

import re

s = "This is a %(name)s example string %(foo)s I would like %(bar)s to extract all the placeholders from %(place)s"
print(re.findall(r"%\((.*?)\)", s))
# --> ['name', 'foo', 'bar', 'place']

使用 collections.defaultdict

from collections import defaultdict


main_list = [["user1@test.com", "Administration", "100"],
             ["user2@test.com", "Testing", "30"],
             ["user2@test.com", "Development", "45"],
             ["user2@test.com", "Development", "90"],
             ["user2@test.com", "Development", "35"],
             ["user3@test.com", "Development", "400"],
             ["user3@test.com", "Administration", "95"],
             ["user3@test.com", "Testing", "200"]]
result = defaultdict(int)
for k, v, n in main_list:
    result[(k, v)] += int(n)
result = [list(k) + [v] for k, v in result.items()]
print(result)

输出:

[['user1@test.com', 'Administration', 100],
 ['user2@test.com', 'Testing', 30],
 ['user2@test.com', 'Development', 170],
 ['user3@test.com', 'Development', 400],
 ['user3@test.com', 'Administration', 95],
 ['user3@test.com', 'Testing', 200]]

使用 next(input_reader) 获取标题,然后附加新列名并将其写回csv。

with open('simpleexcel.csv', 'r') as f_input:  # Declared variable f_input to open and read the input file
    input_reader = csv.reader(f_input)  # this will iterate ober lines from input file

    with open('Outputfile.csv', "w", newline='') as f_output:  # opens a file for qwriting in this case outputfile
        line_writer = csv.writer(f_output) #If csvfile is a file object, it should be opened with newline=''
        line_writer.writerow(next(input_reader) + ["Age"]))  #Write Header
        for line in input_reader: #prints every row
            line_writer.writerow(line+['14'])

你可以用 enumerate

前任:

x = [1,2,3,4,5,6,7,8,9,10,11,12,13,14,15]
y = [None,None,None,None,None,10,20,30,40,50,60,70,80,90,100]

result = []
for i, v in enumerate(x[5:], 5):
    result.append(v - y[i])
print(result)

[-4, -13, -22, -31, -40, -49, -58, -67, -76, -85]

你可以用 range

前任:

data=[]

for _ in range(2):
    name = raw_input("Please enter your name: ")
    age = int(raw_input("Please enter your age: "))
    height = int(raw_input("Please enter your height: "))
    data.append((name, age, height))
print(data)

或: 使用while循环。

data=[]

while True:
    name = raw_input("Please enter your name: ")
    age = int(raw_input("Please enter your age: "))
    height = int(raw_input("Please enter your height: "))
    data.append((name, age, height))

    if len(data) == 2:
        break

print(data)

您也可以使用 csv 模块。

前任:

import csv

s = '"BLAX", "BLAY", "BLAZ, BLUBB", "BLAP"' 
r = csv.reader(s, delimiter = ',', quotechar='"')
res = [j for i in r for j in i if j.strip()] 
print(res)  

输出:

['BLAX', 'BLAY', 'BLAZ, BLUBB', 'BLAP']

使用 collections.Counter

前任:

from collections import Counter

example = [('dog'),('dog'),('cat'),('cat'),('fish'),('frog'),('frog')]
c = Counter(example)
print(c.most_common(3))

输出:

[('dog', 2), ('frog', 2), ('cat', 2)]

您可以使用嵌套列表理解

前任:

from bs4 import BeautifulSoup

html = """<ul>
<li>
  <div>Content1</div>
</li>
<li>
  <div>Content2</div>
  <div>Content3</div>
  <div>Content4</div>
</li>
<li>
  <div>Content5</div>
  <div>Content6</div>
</li>
</ul>"""

soup = BeautifulSoup(html, "html.parser")
print([[j.get_text(strip=True) for j in i.find_all("div")] for i in soup.find_all("li")])

输出:

[['Content1'], ['Content2', 'Content3', 'Content4'], ['Content5', 'Content6']]

你可能需要使用 %2B

前任:

http://exaple.com/api/v1/get_example/?fruits_name=[apple%20%2B%20banana]

Reference

这是一种使用简单迭代的方法。

前任:

s = """TASK000123-Tomcat server hosted on tbu.test1 is down-P1 --In Progress
TASK000123-Tomcat server hosted on tbu.test1 is down-P1 --Completed"""

result = [["TaskID","Priority","Status"]]

for i in s.splitlines():
    val = i.split("-")                          #Split by '-'
    result.append([val[0], val[2], val[-1]])
print(result)

产量:

[['TaskID', 'Priority', 'Status'],
 ['TASK000123', 'P1 ', 'In Progress'],
 ['TASK000123', 'P1 ', 'Completed']]

使用regex模式 r"\"variants\":\[(.*?)\]"

演示:

from bs4 import BeautifulSoup
import json
import re

s = """<script>var BOLD = BOLD || {};
    BOLD.products = BOLD.products || {};
    BOLD.variant_lookup = BOLD.variant_lookup || {};BOLD.variant_lookup[31066737740] ="womanizer";BOLD.variant_lookup[31066737804] ="womanizer";BOLD.variant_lookup[31066737868] ="womanizer";BOLD.variant_lookup[31066737996] ="womanizer";BOLD.variant_lookup[1509908217881] ="womanizer";BOLD.products["womanizer"] ={"id":8993669708,"title":"Womanizer","variants":[{"id":37834367948,"title":"Black","option1":"Black","option2":null,"option3":null,"sku":"1725205212"}]}
    </script>
"""

soup = BeautifulSoup(s, "html.parser")
src = soup.find("script")
m = re.search(r"\"variants\":\[(.*?)\]", src.string)
if m:
    data = json.loads(m.group(1))
    print(data)

输出:

{u'sku': u'1725205212', u'title': u'Black', u'id': 37834367948L, u'option2': None, u'option3': None, u'option1': u'Black'}

使用 collections.defaultdict

前任:

from collections import defaultdict

res = defaultdict(list)

with open(filename) as infile:
    for line in infile:                      #Iterate each line
        val = line.strip().split()           #Get first word
        res[val[0]].append(line)

for k, v in res.items():
    if len(v) > 1:
        print(v)

输出:

['G1/0/1    fc:3f:db:8d:fd:6c\n', 'G1/0/1    38:63:bb:bb:f8:7d\n']

这是一种使用简单迭代的方法。

前任:

from collections import defaultdict
dict_ot={"Berlin":4, "London":3,"Madrid":3,"Germany":51, "Others":1, "France":4}
grpBy = [("Germany", "Berlin"), ("Madrid", "Others"), ("London",)]
res = defaultdict(int)
for i in grpBy:
    for j in i:
        res[i] += dict_ot[j]

for k, v in res.items():
    print("{}: {}".format(", ".join(k), v))

输出:

Germany, Berlin: 55
London: 3
Madrid, Others: 4

import os
import glob

path = '/users/user/folder'
for f in glob.iglob(path+'/**/*.xlsx', recursive=True):
    os.remove(f)